© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 129157
    Prev
    Next
    INDEX
    Explanations

    structure and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    三个
    0.47
    urta
    0.47
    াল
    0.46
     coisa
    0.45
     instead
    0.44
    观
    0.44
    两条
    0.44
     scratches
    0.43
     riesce
    0.43
    ως
    0.43
    POSITIVE LOGITS
     розви
    0.46
     نش
    0.43
     Б
    0.42
     بزرگ
    0.41
     اجمع
    0.41
     lekker
    0.41
     لاعب
    0.40
     دشمن
    0.40
     배
    0.39
     règne
    0.39
    Activations Density 0.003%

    No Known Activations